An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks

2021/05/19 by Cong Xu, Xiang Li, Xu, Cong +3
Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Fault Detection and Control Systems

paper · pdf · doi:10.48550/arxiv.2105.09109

openalex publication_date 2021/05/19 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28

Abstract

Neural networks are susceptible to artificially designed adversarial perturbations. Recent efforts have shown that imposing certain modifications on classification layer can improve the robustness of the neural networks. In this paper, we explicitly construct a dense orthogonal weight matrix whose entries have the same magnitude, thereby leading to a novel robust classifier. The proposed classifier avoids the undesired structural redundancy issue in previous work. Applying this classifier in standard training on clean data is sufficient to ensure the high accuracy and good robustness of the model. Moreover, when extra adversarial samples are used, better robustness can be further obtained with the help of a special worst-case loss. Experimental results show that our method is efficient and competitive to many state-of-the-art defensive approaches. Our code is available at \urlhttps://github.com/MTandHJ/roboc.

Related

• Improve Adversarial Robustness via Weight Penalization on Classification Layer
• Learning with a Strong Adversary
• Neural Networks in Adversarial Setting and Ill-Conditioned Weight Space
• Towards Adversarial Training with Moderate Performance Improvement for Neural Network Classification
• A3T: Adversarially Augmented Adversarial Training